Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ktnCodes/icm-template --skill icm-scaffoldgit clone --depth 1 https://github.com/ktnCodes/icm-templateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ktncodes/icm-template/icm-scaffold)<a href="https://agentmods.dev/skills/ktncodes/icm-template/icm-scaffold"><img src="https://agentmods.dev/badge/skills/ktncodes/icm-template/icm-scaffold.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02342 |
| Opus 5 | $0.00000 | $0.01171 |
| Sonnet 5 | $0.00000 | $0.00468 |
| Haiku 4.5 | $0.00000 | $0.00234 |
Grade A, and why
icm-scaffold scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ICM Scaffold
Set up an ICM (Interpretable Context Methodology) workspace on any project — generating IDENTITY.md (Layer 0), CONTEXT.md (Layer 1), and _config/ (Layer 3) files tailored to the project's domain, folder structure, and workflow.
Based on the ICM research paper by Jake Van Clief and David McDermott, extended with Karpathy's knowledge base pattern (raw → compile → wiki → Q&A). Encodes a proven workflow tested on engineering documentation, content pipelines, and personal knowledge bases.
Key framing: The LLM is a compiler, not a chatbot. Stage contracts define inputs and structured outputs. The LLM reads sources, compiles structured deliverables, and writes them to specific locations. Conversations happen during review gates, not during execution.
Interview
Before generating any files, ask the user these questions. Accept brief answers — infer reasonable defaults where possible.
Required
- What project is this for? (project name + one sentence description)
- Where does the project live? (root directory path)
- What does the folder structure look like? (list the directory or ask to scan it)
- What are the main workflow tasks? (e.g., "compile docs from source notes", "research → draft → review", "investigate bugs → implement → test")
- Does this project involve knowledge compilation? (i.e., raw sources → structured articles/docs/wiki) If yes, the pipeline uses the compilation archetype. If no, use generic stage contracts.
- Who is the audience for the outputs? (engineers, general public, LLM agents, mixed)
Optional (infer defaults if not answered)
- What voice/tone should outputs use? Default: match the existing content style.
- Are there existing conventions files? (coding standards, glossary, style guides) — if yes, reference them instead of duplicating.
- What model adapters do you need? (Claude Code / Cursor / Copilot / Windsurf / none) Default: none — IDENTITY.md works with any model.
- Quick mode or full mode?
- Quick (3-layer): IDENTITY.md + CONTEXT.md + _config/ — routing and reference only. Best for adding ICM to an existing project without restructuring.
- Full (5-layer): All of quick mode + physical stage folders with CONTEXT.md contracts + output/ directories. Best for new pipelines built from scratch.
- Default: Quick — earn complexity before adding it.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 168 lines · 0 tokens per session scan A 33dc01dff961
icm-scaffold is a skill published in the GitHub repository ktnCodes/icm-template (53 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,342 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.